Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.5914. Min Range: -18.5914
Max Act: 18.5914. Min Act: -0.1697
Data Index: 4177970 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.7164. Min Act: -0.1697
Data Index: 1334837 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.4664. Min Act: -0.1700
Data Index: 2616757 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.4664. Min Act: -0.1700
Data Index: 4282094 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.3414. Min Act: -0.1700
Data Index: 417091 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.3414. Min Act: -0.1700
Data Index: 7384799 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.3414. Min Act: -0.1700
Data Index: 2800282 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.5914. Min Range: -18.5914
Max Act: 17.0914. Min Act: -0.1700
Data Index: 6512802 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 650055 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 8480875 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.8414. Min Act: -0.1700
Data Index: 3969312 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 1199588 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 5358839 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 6932984 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 2883210 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 7342481 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 8070955 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.8414. Min Act: -0.1700
Data Index: 5131293 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.7164. Min Act: -0.1700
Data Index: 2329324 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.5914. Min Range: -18.5914
Max Act: 16.9664. Min Act: -0.1700
Data Index: 4753624 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19